Related Experiment Video
Updated: Jun 4, 2026

A Method for Manipulating Blood Glucose and Measuring Resulting Changes in Cognitive Accessibility of Target Stimuli
Published on: August 12, 2016
Genetic-algorithm-based multiple regression with fuzzy inference system for detection of nocturnal hypoglycemic
Steve S H Ling1, Hung T Nguyen
1Centre for Health Technologies, Faculty of Engineeringand Information Technology, University of Technology, Sydney, NSW 2007, Australia. steve.ling@uts.edu.au
A new noninvasive monitor uses physiological data to detect hypoglycemia, a dangerous side effect of insulin therapy in type 1 diabetes mellitus (T1DM) patients. This system shows promise for early detection of low blood glucose episodes.
Area of Science:
- Biomedical Engineering
- Medical Informatics
- Endocrinology
Background:
- Hypoglycemia is a dangerous complication of insulin therapy in diabetes.
- Noninvasive monitoring for hypoglycemic episodes in type 1 diabetes mellitus (T1DM) patients is needed.
- Physiological parameters like heart rate and ECG intervals may indicate hypoglycemia.
Purpose of the Study:
- To develop and evaluate a noninvasive monitoring system for detecting hypoglycemic episodes in T1DM patients.
- To utilize a genetic algorithm-based fuzzy inference system for classifying hypoglycemia.
- To assess the association between heart rate, corrected QT interval, and nocturnal hypoglycemia.
Main Methods:
- A genetic algorithm (GA) was used to optimize a fuzzy inference system (FIS) combined with multiple regression.
- The system analyzes heart rate (HR) and corrected QT interval (cQT) from ECG signals.
- Data from 16 T1DM children with naturally occurring nocturnal hypoglycemia were used for training and testing.
Main Results:
- The developed GA-based FIS model effectively classified hypoglycemic episodes.
- Nocturnal hypoglycemia was associated with changes in HR and cQT intervals.
- The algorithm demonstrated good sensitivity and acceptable specificity in detecting hypoglycemia.
Conclusions:
- A noninvasive GA-based FIS model can accurately detect hypoglycemic episodes in T1DM patients.
- Continuous monitoring of HR and cQT intervals offers a potential method for hypoglycemia detection.
- This approach could improve the management and safety of insulin therapy for T1DM.
Related Concept Videos
Hypoglycemia and Glucagon
Hypoglycemia
Hormones Regulating Blood Glucose
In addition to accelerating glucose uptake and utilization, insulin has...
Hyperglycemia
Glucose Homeostasis: Regulation of Blood Glucose
During fasting, when blood glucose levels are low, the pancreas secretes glucagon. it...